Icon

01_​Modelling_​Workflow_​with_​Manual_​Deployment

Training Workflow with Manual Deployment

This workflow shows a simple example of churn prediction with interactive threshold optimization. This workflow is used for comparison before Integrated Deployment was introduced with KNIME 4.2. You can see how the trained models are manually saved via Model Writer nodes.

training set test set Reading and Blending - contract data + churn - behavioral (calls) data Pre-processing - Join contract data and behavioral data - Convert Churn values to String to be used as class in upcoming classification - Reserve 80% of the rows for model training and remaining for model testing - Missing value imputation modelling Train and Optimize Score Evaluate predictions based on confusion matrix views. - Optimize Random Forest parameters - Optimize threshold Binary Classification - Train model with optimized parameters Churn = 0 : current subscriptions Churn = 1 : cancelled subscriptions train set test set Deploy Save Models train: 80% test: 20%Area codeand churn 0/1are converted toString. optimize thresholdapply newthresholdoptimized thresholddefault 50% thresholdReadingContractData.csvsave missing value modelSave Random Forest ModelJoin the contract data and the behavioral data DB Table Selector DB Connector Partitioning Number To String Random ForestLearner Random ForestPredictor Missing Value Missing Value(Apply) Binary ClassificationInspector Rule Engine Scorer (JavaScript) Scorer (JavaScript) DB Reader Domain Calculator File Reader Model Writer Model Writer Joiner Column Filter Table Rowto Variable Database URL andCredentials ParameterOptimization training set test set Reading and Blending - contract data + churn - behavioral (calls) data Pre-processing - Join contract data and behavioral data - Convert Churn values to String to be used as class in upcoming classification - Reserve 80% of the rows for model training and remaining for model testing - Missing value imputation modelling Train and Optimize Score Evaluate predictions based on confusion matrix views. - Optimize Random Forest parameters - Optimize threshold Binary Classification - Train model with optimized parameters Churn = 0 : current subscriptions Churn = 1 : cancelled subscriptions train set test set Deploy Save Models train: 80% test: 20%Area codeand churn 0/1are converted toString. optimize thresholdapply newthresholdoptimized thresholddefault 50% thresholdReadingContractData.csvsave missing value modelSave Random Forest ModelJoin the contract data and the behavioral data DB Table Selector DB Connector Partitioning Number To String Random ForestLearner Random ForestPredictor Missing Value Missing Value(Apply) Binary ClassificationInspector Rule Engine Scorer (JavaScript) Scorer (JavaScript) DB Reader Domain Calculator File Reader Model Writer Model Writer Joiner Column Filter Table Rowto Variable Database URL andCredentials ParameterOptimization

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: paolotamag
Created at: 2020-03-03
On NodePit since: 2020-07-17
Last update: 2024-04-23
Created with KNIME version: v4.5.1
Tags: manual deploymentthreshold optimizationbinary classificationchurn prediction

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!